Bertha (Lily) Gonzalez
MPH 505
1. This article is arguing that evaluating studies based on hypothesis testing and the use of the P value does not always provide the expected findings, especially for medical professionals.
The author of the article mentioned that the use of a confidence interval may present a better picture of the measurement of the data.
Confidence intervals must be the standard of presenting results in major findings this is what the article indicated.
2. In the introduction, the authors describe a scenario involving mean concentrations of a blood constituent. They point out that readers should want to know "how much the illness modified the mean blood concentrations... rather than only the level of statistical significance." Do you agree with this statement? Why or why not?
Yes I agree with these statements. The method that statisticians use to present reports does not always satisfy the expectations of the clinicians or answer their questions and concerns. “Statistically significant or not significant” may be essential for statistical reports but clinical providers and other medical professionals need more practical and human friendly information. In the case of medication for example; a clinician may like to know where and how the medication metabolizes, the side effects, and if is safe during pregnancy or when nursing. This is the information that health professionals and general public are looking for.
3. In the section titled Presentation of study results: limitation of P values, the authors state that simply presenting P values "encourages lazy thinking." What do you think is meant by this statement? Do you agree with it? Why or why not?
Yes…I support the conclusion the author made about “lazy thinking” because a simple statistical number does not describe the sample. This limited information interferes with critical thinking from the readers anddoes not allow the reader to see opportunities to overcome health concerns.
The author even mentioned that the use of P values in large samples may evaluate small differences like significant facts and may put clinically important information as not significant in small samples. That isvery important information to take in consideration.
4. after reading this article, do you have any hesitations about doing hypothesis testing? Explain why or why not.
No, I believe that the use of hypothesis can give you a direction to begin the research. However after reading the article I learned that confidence interval provides a more clear examination of the measurement of data, which is extremely important. I am a clinician and a community health educator and for me the knowledge and information that I obtain from medical literature is essential to provide a professional care for my patients, although what I have encountered in the real world is sometimes different to whatI learned in the books.
For my job I will take in consideration both approaches to analyze data. But ultimately the patient is the expert in his / her necessities even though the findings in the studies may say something different.
Gardner J. Martin, Altman G. Douglas (1986) Confidence Intervals rather than P values: estimation rather than Hypothesis testing. British Medical Journal